Llamacpp Quantizations of Starling_Monarch_Westlake_Garten-7B-v0.1
Using llama.cpp release b2440 for quantization.
Original model: https://huggingface.co./giraffe176/Starling_Monarch_Westlake_Garten-7B-v0.1
Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q8_0.gguf | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q6_K.gguf | Q6_K | 5.94GB | Very high quality, near perfect, recommended. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q5_K_M.gguf | Q5_K_M | 5.13GB | High quality, very usable. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q5_K_S.gguf | Q5_K_S | 4.99GB | High quality, very usable. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q5_0.gguf | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q4_K_M.gguf | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q4_K_S.gguf | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-IQ4_NL.gguf | IQ4_NL | 4.15GB | Good quality, similar to Q4_K_S, new method of quanting, |
| Starling_Monarch_Westlake_Garten-7B-v0.1-IQ4_XS.gguf | IQ4_XS | 3.94GB | Decent quality, new method with similar performance to Q4. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q4_0.gguf | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-IQ3_M.gguf | IQ3_M | 3.28GB | Medium-low quality, new method with decent performance. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-IQ3_S.gguf | IQ3_S | 3.18GB | Lower quality, new method with decent performance, recommended over Q3 quants. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q3_K_L.gguf | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q3_K_M.gguf | Q3_K_M | 3.51GB | Even lower quality. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q3_K_S.gguf | Q3_K_S | 3.16GB | Low quality, not recommended. |
| Starling_Monarch_Westlake_Garten-7B-v0.1-Q2_K.gguf | Q2_K | 2.71GB | Extremely low quality, not recommended. |
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
- Downloads last month
- 81
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for bartowski/Starling_Monarch_Westlake_Garten-7B-v0.1-GGUF
Merge model
this model
Evaluation results
- self-reported on EQ-BenchEQ-Bench v2.180.010
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard71.760
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard88.150
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard65.070
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard67.920
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard82.160
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard71.950